Data science is one collective term that is on everyone’s mouth these days, with its applications now being used across big companies, research institutes, and college projects. Since data science is utilised in every sector these days, it is crucial to have a sound knowledge of this vast subject. Although a wide range of information can be found on any search engine, the wiser step is to read materials that have been carefully penned down by experts from the field and are available in the form of e-Books.Data science is one collective term that is on everyone’s mouth these days, with its applications now being used across big companies, research institutes, and college projects. Since data science is utilised in every sector these days, it is crucial to have a sound knowledge of this vast subject. Although a wide range of information can be found on any search engine, the wiser step is to read materials that have been carefully penned down by experts from the field and are available in the form of e-Books. Read More
Monthly Archives: February 2020
Multimodal Matching Transformer for Live Commenting
Automatic live commenting aims to provide real-time comments on videos for viewers. It encourages users engagement on online video sites, and is also a good benchmark for video-to-text generation. Recent work on this task adopts encoder-decoder models to generate comments. However, these methods do not model the interaction between videos and comments explicitly, so they tend to generate popular comments that are often irrelevant to the videos. In this work, we aim to improve the relevance between live comments and videos by modeling the cross-modal interactions among different modalities. To this end, we propose a multimodal matching transformer to capture the relationships among comments, vision, and audio. The proposed model is based on the transformer framework and can iteratively learn the attention-aware representations for each modality. We evaluate the model ona publicly available live commenting dataset. Experiments show that the multimodal matching transformer model outperforms the state-of-the-art methods. Read More
Phantom of the ADAS
The absence of deployed vehicular communication systems, which prevents the advanced driving assistance systems (ADASs) and autopilots of semi/fully autonomous cars to validate their virtual perception regarding the physical environment surrounding the car with a third party, has been exploited in various attacks suggested by researchers. Since the application of these attacks comes with a cost (exposure of the attacker’s identity), the delicate exposure vs. application balance has held, and attacks of this kind have not yet been encountered in the wild. In this paper, we investigate a new perceptual challenge that causes the ADASs and autopilots of semi/fully autonomous to consider depthless objects (phantoms) as real. We show how attackers can exploit this perceptual challenge to apply phantom attacks and change the abovementioned balance, without the need to physically approach the attack scene, by projecting a phantom via a drone equipped with a portable projector or by presenting a phantom on a hacked digital billboard that faces the Internet and is located near roads. We show that the car industry has not considered this type of attack by demonstrating the attack on today’s most advanced ADAS and autopilot technologies: Mobileye 630 PRO and the Tesla Model X, HW 2.5; our experiments show that when presented with various phantoms, a car’s ADAS or autopilot considers the phantoms as real objects, causing these systems to trigger the brakes, steer into the lane of oncoming traffic, and issue notifications about fake road signs. In order to mitigate this attack, we present a model that analyzes a detected object’s context, surface, and reflected light, which is capable of detecting phantoms with 0.99 AUC. Finally, we explain why the deployment of vehicular communication systems might reduce attackers’ opportunities to apply phantom attacks but won’t eliminate them. Read More
Phantom Attacks Against Advanced Driving Assistance Systems
Automated machine learning or AutoML explained
The two biggest barriers to the use of machine learning (both classical machine learning and deep learning) are skills and computing resources. You can solve the second problem by throwing money at it, either for the purchase of accelerated hardware (such as computers with high-end GPUs) or for the rental of compute resources in the cloud (such as instances with attached GPUs, TPUs, and FPGAs).
On the other hand, solving the skills problem is harder. Data scientists often command hefty salaries and may still be hard to recruit. Google was able to train many of its employees on its own TensorFlow framework, but most companies barely have people skilled enough to build machine learning and deep learning models themselves, much less teach others how. Read More
ARM’s new edge AI chips promise IoT devices that won’t need the cloud
Edge AI is one of the biggest trends in chip technology. These are chips that run AI processing on the edge — or, in other words, on a device without a cloud connection. Apple recently bought a company that specializes in it, Google’s Coral initiative is meant to make it easier, and chipmaker ARM has already been working on it for years. Now, ARM is expanding its efforts in the field with two new chip designs: the Arm Cortex-M55 and the Ethos-U55, a neural processing unit meant to pair with the Cortex-M55 for more demanding use cases. Read More
#011 Deep L-layer Neural Network
In this post we will make a Neural Network overview. We will see what is the simplest representation of a Neural Network and how deep representation of a Neural Network looks like.
The Link Between Sleep and Deep Learning
The cognitive purpose of sleep is an open question. Recently, however, scientists have a new conjecture (“How memory replay in sleep boosts creative problem solving“) as to the purpose of two important phases of sleep.
According to the research, the brain goes through several 90-minute cycles of REM and Non-REM sleep. Non-REM sleep involves the sequential replay of acquired memories. In contrast, REM sleep involves a more random associate game involving disparate memories. In deep learning, this is analogous to the search algorithms of optimization and exploration respectively. Read More
Competing in the Age of AI
In 2019, just five years after the Ant Financial Services Group was launched, the number of consumers using its services passed the one billion mark. Spun out of Alibaba, Ant Financial uses artificial intelligence and data from Alipay—its core mobile-payments platform—to run an extraordinary variety of businesses, including consumer lending, money market funds, wealth management, health insurance, credit-rating services, and even an online game that encourages people to reduce their carbon footprint. The company serves more than 10 times as many customers as the largest U.S. banks—with less than one-tenth the number of employees. At its last round of funding, in 2018, it had a valuation of $150 billion—almost half that of JPMorgan Chase, the world’s most valuable financial-services company. Read More
Rick's Cafe AI 